Models
Image and text models behind the same API key and the same balance. Image models are priced per image, chat models per 1M tokens; the money figures are the equivalent at our best-value credit pack.
Image models (6)
nanobanana· GoogleFast, general-purpose text-to-image and image-to-image generation at 1K, behind a single HTTP endpoint. Billed per image in credits, refunded automatically when a job fails.
- Resolutions:
- 1K
- Images per request:
- 4
from 2 credits ≈ $0.025 / image
Nano Banana API — pricing and quick start →
nanobanana-pro· GoogleHigher-fidelity generation for hero shots and print-sized crops, with 1K, 2K and 4K output — roughly twice the base price per image at 1K.
- Resolutions:
- 1K · 2K · 4K
- Images per request:
- 4
from 4 credits ≈ $0.05 / image
Nano Banana Pro API — pricing and quick start →
qwen-image-2· AlibabaQwen-Image 2.0 from Alibaba — an image model built around legible in-image text, including Chinese, with reference-image input and 1K or 2K output.
- Resolutions:
- 1K · 2K
- Images per request:
- 4
from 3 credits ≈ $0.038 / image
Qwen-Image 2.0 API — pricing and quick start →- qwen-image-max· Alibaba
Qwen-Image Max — the flagship of Alibaba's Qwen-Image line, with reference-image input, 1K and 2K output and a fixed set of five aspect ratios.
- Resolutions:
- 1K · 2K
- Images per request:
- 4
from 8 credits ≈ $0.10 / image
Qwen-Image Max API — pricing and quick start → - seedream-5· ByteDance
ByteDance Seedream 5.0 — a high-resolution model for photoreal frames and in-image text, served at 2K and 4K only. Takes reference images, billed per image in credits.
- Resolutions:
- 2K · 4K
- Images per request:
- 4
from 16 credits ≈ $0.20 / image
Seedream 5.0 API — pricing and quick start → 
wan-2-7-image· Alibabawan2.7-image from Alibaba's Tongyi Wanxiang line — text-to-image and reference-image generation at 1K or 2K, on the same endpoint and API key as every other model here.
- Resolutions:
- 1K · 2K
- Images per request:
- 4
from 2 credits ≈ $0.025 / image
Wan 2.7 Image API — pricing and quick start →
Text models (10)
doubao-seed-2-pro· ByteDanceByteDance's flagship Doubao model with vision and web search — for complex reasoning and multimodal tasks. 256K-token context, streaming and an OpenAI-compatible endpoint, billed per token in prepaid credits — no subscription.
- Context:
- 256K
- Max output:
- 16,384
- Features:
- tool calling · thinking · web search · vision · streaming
85 in · 408 out credits / 1M
$1.063 in · $5.10 out
Doubao Seed 2.0 Pro API — pricing and quick start →- doubao-seed-2-code· ByteDance
Doubao's coding-tuned model with vision — for agentic coding, refactors and UI-from-screenshot tasks. 256K-token context, streaming and an OpenAI-compatible endpoint, billed per token in prepaid credits — no subscription.
- Context:
- 256K
- Max output:
- 16,384
- Features:
- tool calling · thinking · vision · streaming
85 in · 408 out credits / 1M
$1.063 in · $5.10 out
Doubao Seed 2.0 Code API — pricing and quick start → - doubao-seed-2-lite· ByteDance
Mid-tier Doubao model with vision — general assistants and image-aware chat at a lower cost than Pro. 256K-token context, streaming and an OpenAI-compatible endpoint, billed per token in prepaid credits — no subscription.
- Context:
- 256K
- Max output:
- 16,384
- Features:
- thinking · vision · streaming
17 in · 85 out credits / 1M
$0.213 in · $1.063 out
Doubao Seed 2.0 Lite API — pricing and quick start → - doubao-seed-2-mini· ByteDance
The cheapest Doubao model with vision — high-volume, latency-sensitive chat and simple image tasks. 256K-token context, streaming and an OpenAI-compatible endpoint, billed per token in prepaid credits — no subscription.
- Context:
- 256K
- Max output:
- 16,384
- Features:
- vision · streaming
2.146 in · 68 out credits / 1M
$0.027 in · $0.85 out
Doubao Seed 2.0 Mini API — pricing and quick start → 
kimi-k3· MoonshotMoonshot's flagship Kimi model with a huge context window — for very long documents and multi-step agents. 1M-token context, streaming and an OpenAI-compatible endpoint, billed per token in prepaid credits — no subscription.
- Context:
- 1M
- Max output:
- 16,384
- Features:
- tool calling · streaming
claude-opus-5-5· AnthropicAnthropic's top Claude Opus model — strong reasoning and agentic coding with a large context window for complex, multi-step work. 200K-token context, streaming and an OpenAI-compatible endpoint, billed per token in prepaid credits — no subscription.
- Context:
- 200K
- Max output:
- 16,384
- Features:
- tool calling · streaming
146.88 in · 734.4 out credits / 1M
$1.836 in · $9.18 out
Claude Opus 5.5 API — pricing and quick start →- claude-fable-5-1· Anthropic
Anthropic's premium Claude model for long-form writing — polished drafting and editing with a large context window. 200K-token context, streaming and an OpenAI-compatible endpoint, billed per token in prepaid credits — no subscription.
- Context:
- 200K
- Max output:
- 16,384
- Features:
- tool calling · streaming
1,700 in · 1,700 out credits / 1M
$21.25 in · $21.25 out
Claude Fable 5.1 API — pricing and quick start → 
gpt-6-astra· OpenAIOpenAI's general-purpose flagship — balanced reasoning, chat and tool use for everyday production assistants. 128K-token context, streaming and an OpenAI-compatible endpoint, billed per token in prepaid credits — no subscription.
- Context:
- 128K
- Max output:
- 16,384
- Features:
- tool calling · streaming
- gpt-5.6-terra· OpenAI
OpenAI's fast, economical GPT model for high-volume chat, drafting and tool use where cost and latency matter most. 128K-token context, streaming and an OpenAI-compatible endpoint, billed per token in prepaid credits — no subscription.
- Context:
- 128K
- Max output:
- 16,384
- Features:
- tool calling · streaming
qwen3.8-max· AlibabaAlibaba's newest flagship Qwen model, with a very large context window and solid tool use — a sensible default for most agent and reasoning work. 1M-token context, streaming and an OpenAI-compatible endpoint, billed per token in prepaid credits — no subscription.
- Context:
- 1M
- Max output:
- 16,384
- Features:
- tool calling · streaming
138.718 in · 416.161 out credits / 1M
$1.734 in · $5.202 out
Qwen3.8-Max API — pricing and quick start →
USD figures are converted at the Scale pack rate; larger packs are cheaper per credit. See pricing for the full pack list.